CODEWITHSUNDEEP
pythonnumpy
harry123
harry123

Reputation: 910

Add data to MNIST dataset

I am doing a machine learning project to recognize handwritten digits. Actually, I just want to add few more data sets to MNIST but I am unable to do so.

I have done following:

n_samples = len(mnist.data)
x = mnist.data.reshape((n_samples, -1))# array of feature of 64 pixel
y = mnist.target                         # Class label from 0-9 as there are digits

img_temp_train=cv2.imread('C:/Users/amuly/Desktop/Soap/crop/2.jpg',0)

X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.2)

#Now I want to add the img_temp_train to my dataset for training.

X_train=np.append(X_train,img_temp_train.reshape(-1))
y_train=np.append(y_train,[4.0])

The length after training is:

But it should be 56001 for both.

Upvotes: 1

Views: 1774

Answers (1)

Mateen Ulhaq
Mateen Ulhaq

Reputation: 27201

Try this:

X_train = np.append(X_train, [img_temp_train], axis=0)

You shouldn't be reshaping things willy-nilly without thinking about what you're doing first!

Also, it's usually a better idea to use concatenate:

X_train = np.concatenate((X_train, [img_temp_train]), axis=0)

Upvotes: 1

Related Questions